On Uncertainty Quantification for Near-Bayes Optimal Algorithms

arXiv:2403.19381v1 Announce Type: cross
Abstract: Bayesian modelling allows for the quantification of predictive uncertainty which is crucial in safety-critical applications. Yet for many machine learning (ML) algorithms, it is difficult to construct or implement their Bayesian counterpart. In this work we present a promising approach to address this challenge, based on the hypothesis that commonly used ML algorithms are efficient across a wide variety of tasks and may thus be near Bayes-optimal w.r.t. an unknown task distribution. We prove that …

abstract algorithms applications arxiv bayes bayesian challenge construct cs.lg hypothesis machine machine learning modelling near predictive quantification safety safety-critical stat.ml type uncertainty work